Open Access Open Access  Restricted Access Subscription or Fee Access

Convolutional Neural Network Algorithm for Stress Field Approximation for a Uniaxially Loaded Plate with Holes

Prajwal S. H, Lingareddy Manoj Kumar, Abhinandan Rao

Abstract


ABSTRACT

Knowing the high stress concentration and its location around a hole is of practical importance in designing engineering structures, effective parameters can be selected in order to achieve minimum stress concentration around the hole(s). The visualisation of the stress distribution is done experimentally or numerically using finite element analysis (FEA). This study involved the approximation of the von Mises stress field distribution around regular holes in finite metallic plates, based on deep learning 2D encoder-decoder convolutional neural network (CNN). The CNN based stress field prediction is achieved by nonlinear 2D image training data obtained from ABAQUS, the geometric parameter of flat plate and the hole(s) are the input to CNN and the von Mises stress filed distribution is the output, assuming the plate considered is finite, isotropic, plane stress state, linearly elastic and uniaxial loading condition with total number of trainable parameters for the neural network is 3,437,143. The prediction accuracy achieved is 94.18% with a loss of 0.03% between the ground truth and the predicted images Considerable care was taken to minimize the complexity of the CNN architecture and to make it interpretable and to achieve high accuracy with available low data. The proposed method can predict acceptable accurate solution to a problem with the geometries not included in the training dataset. This approach can be directly applied as it provides immediate feedback for real-time design iterations at the early stage of design.

 

Keywords: Convolutional neural network, finite element analysis, isotropic plate, machine learning, regular hole, stress concentration, uniaxial loading


Full Text:

PDF

References


REFERENCES

Peterson R. (n.d.). Stress concentration design factors. United states: John Wiley & Sons.

Jafari M, Ardalani, et al. Stress concentration in finite metallic plates with regular holes. Int J Mech Sci. 2015; 106: 220–230p.

Muskhelishvili N. Some basic problems of the mathematical theory of elasticity. Fourth, corrected and augmented edition mosco 1954, translated from russian by J. R. M. Rado K, Springer. 190p. doi:10.1007/978-94-017-3034-1

Chen HC. Special finite elements including stress concentration. Finite Elem Anal Des. 1993; 13(4): 249–258p.

Jianlin Wang, Steven L. Crouch, et al. A complex boundary integral method for multiple circular holes in an infinite plate. Eng Anal Boundary Elements. 2003; (27): 789–802p.

Sharma SD. Stress distribution around polygonal holes. Int J Mech Sci. 2012; (65): 115–124p.

Rezaeepazhand J, Jafari, et al. Stress concentration in metallic plates with special shaped cutout. Int J Mech Sci. 2010; (52): 96–102p.

Zuxing Pan, Yuansheng Cheng, et al. Stress analysis of a finite plate with a rectangular hole subjected to uniaxial tension using modified stress functions. Int J Mech Sci. 2013; (75): 265–277p.

Guo X, Li W, et al. Convolutional Neural Networks for Steady Flow Approximation. 2016. Available From: doi:http://dx.doi.org/10.1145/2939672.2939738

Saurabh Banga, Harsh Gehani, et al. 3D Topology Optimization Using Convolutional Neural Networks. Available from https://www.researchgate.net/publication/327173503_3D_Topology_Optimization_using_Convolutional_Neural_Networks

Zhenguo Nie, Haoliang Jiang, et al. stress field prediction in cantilevered structures using convolutional neural networks. J Comput Info Sci Eng. 2019; 20(1).

Oishi A, Yagawa G. Computational mechanics enhanced by deep learning. Comp Method Appl Mech Eng. 2017; (327): 327–351p.

Spruegel T, Schrppel T, et al. Generic approach to plausibility checks for structural mechanics with deep learning. 2017. Available from: https://www.designsociety.org/publication/39529/Generic+approach+to+plausibility+checks+for+structural+mechanics+with+deep+learning

Socher R, Huval B, et al. Convolutional-recursive deep learning for 3d object classification. Adv Neural Info Process Syst. 2012. Available from https://www.researchgate.net/publication/267244277_Convolutional-Recursive_Deep_Learning_for_3D_Object_Classification

Gupta S, Girshick R, et al. Learning rich features from RGB-D images for object detection and segmentation. In Computer Vision-ECCV. 2014.

Liang L, Liu, et al. A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis. J Royal Soc Interface. 2018; 15(138).

Dosovitskiy A, Fischer P, et al. Flownet: Learning optical flow with convolutional networks. In IEEE International Conference on Computer Vision (ICCV). 2015.

Olaf Ronneberger, Philipp Fischer, et al. U-Net: Convolutional Networks for Biomedical Image Segmentation. Cornell University, Comput Vis Patt Recog. 2015. Available from arXiv:1505.04597

Systèmes D. (n.d.). Simulia ABAQUS, 6.14. Retrieved from: www.3ds.com

Lingaiah K, Narayana Iyengar BR. Machine Design Data Handbook (Vol. 1). Suma Publishers. 2006.

Krizhevsky A, Sutskever, et al. Imagenet classification with deep convolutional neural networks. Commun ACM. 2017; 6(60): 84–90p.

Sergey Ioffe, Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Cornell University. 2015. Available from https://arxiv.org/abs/1502.03167

Zeiler MD, Krishnan D, Taylor GW, Fergus R. Deconvolutional networks. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR [5539957] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). 2010, 2528–2535p. Available from: https://doi.org/10.1

/CVPR.2010.5539957

Abien Fred Agarap. Deep learning using rectified linear units (relu). CoRR. 2018. Available From: https://arxiv.org/abs/1803.08375

He K, Zhang X, et al. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. The IEEE International Conference on Computer Vision (ICCV). Santiago, Chile, 2015.

Martín Abadi, Ashish Agarwal, et al. TensorFlow: Large-scale machine learning on heterogeneous systems. 2015. Available from: https://arxiv.org/abs/1603.04467




DOI: https://doi.org/10.37628/ijoippr.v6i2.616

Refbacks

  • There are currently no refbacks.